match_colors

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It usefully discloses that the operation is a statistical transfer, that the reference defaults to the whole picture, and that the selection is honoured. It does not say whether the change is destructive/undoable, which layer is affected when none is named, or how partial strength behaves.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences with the core behaviour front-loaded and the usage hint following. The opening clause is slightly colloquial but not wasteful; no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating image operation with no annotations, no output schema, and 0% schema coverage, the description explains the mechanism and reference sources well but omits the meaning of `strength` and the layer-targeting default. An agent could call it, but would be guessing on two of five inputs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does for the reference family: it explains that reference_layer, reference_path, and reference_region map to another layer, a workspace image, or an [x,y,w,h] region, with whole-picture as default. It leaves `layer` (target selection) and especially `strength` (default 1) undefined, which is a real gap for a 5-parameter tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: transfers the per-channel mean and contrast of a reference onto a layer's colours. The operation is unambiguous and technically precise. It does not explicitly contrast itself with neighbours like adjust_image, auto_enhance, or colorize_lineart, so it stops short of full sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use after pasting or generating an element" gives a concrete trigger condition, and "Respects the selection" tells the agent the operation is scoped to an active selection. No when-not conditions or named alternatives are given, so the agent must infer that other colour tools are not appropriate here.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.